Federated Learning with Non-IID Data.
Citations
2,593 citations
Cites background from "Federated Learning with Non-IID Dat..."
...The authors of [77] showed that, with non-IID local data, performance can be greatly reduced for federated learning....
[...]
...Recent improvements have been focusing on overcoming the statistical challenges [60, 77] and improving security [9, 23] in federated learning....
[...]
1,317 citations
919 citations
Cites background from "Federated Learning with Non-IID Dat..."
...7 [39] Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, and Vikas Chandra....
[...]
...[39] studied the non-iid setting, however, they do not have convergence rate....
[...]
895 citations
701 citations
Cites background or methods from "Federated Learning with Non-IID Dat..."
...accuracy even when data is non-IID across participants, the authors in [65] found otherwise....
[...]
...authors in [76] also propose the LoAdaBoost FedAvg algorithm to complement the aforementioned data-sharing approach [65] in ML on medical data....
[...]
...As we have discussed in Section II-C, the non-IID dataset may significantly degrade the performance of the FedAvg algorithm [65]....
[...]
References
111,197 citations
73,978 citations
42,067 citations
15,005 citations
7,244 citations